Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Generalization of AI-Based Gestational Age Assessment Using Blind Sweep Ultrasonography.

JAMA network open·2026
Same author

Delta Sequential Organ Failure Assessment Within the First 24 Hours as a Predictor of Mortality in Critically Ill Surgical Patients: A Retrospective Study.

Cureus·2026
Same author

Towards Conversational AI for Disease Management.

Nature·2026
Same author

Radiomics-based fundus autofluorescence analysis in central serous chorioretinopathy-MICRoN report number twelve.

Scientific reports·2026
Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026
Same author

Waste water remediation through ultrafast reduction of organic dyes, nitroaromatics, and nitrofuran antibiotics employing efficient multifunctional rGO/Ni-MOF composites.

RSC advances·2026

Related Experiment Video

Updated: Jul 8, 2025

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression
04:36

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

1.1K

Risk Stratification for Diabetic Retinopathy Screening Order Using Deep Learning: A Multicenter Prospective Study.

Ashish Bora1, Richa Tiwari1, Pinal Bavishi1

  • 1Google Health, Palo Alto, CA, USA.

Translational Vision Science & Technology
|December 11, 2023
PubMed
Summary
This summary is machine-generated.

A deep learning model effectively prioritized patients for diabetic retinopathy (DR) screening, showing high sensitivity in identifying those at risk of progression. Real-world application shows promise but requires addressing practical challenges.

More Related Videos

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
05:54

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

286
An Ex Vivo Tissue Culture Model for Fibrovascular Complications in Proliferative Diabetic Retinopathy
08:10

An Ex Vivo Tissue Culture Model for Fibrovascular Complications in Proliferative Diabetic Retinopathy

Published on: January 25, 2019

7.9K

Related Experiment Videos

Last Updated: Jul 8, 2025

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression
04:36

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

1.1K
Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
05:54

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

286
An Ex Vivo Tissue Culture Model for Fibrovascular Complications in Proliferative Diabetic Retinopathy
08:10

An Ex Vivo Tissue Culture Model for Fibrovascular Complications in Proliferative Diabetic Retinopathy

Published on: January 25, 2019

7.9K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Diabetic retinopathy (DR) screening aims to detect progression to moderate or worse (MOD+) stages.
  • Prioritizing follow-up for patients with mild or no DR is crucial for efficient resource allocation.

Purpose of the Study:

  • To conduct a real-world evaluation of a deep learning model for prioritizing patients based on diabetic retinopathy (DR) progression risk.
  • To assess the model's sensitivity in identifying patients likely to develop moderate or worse (MOD+) DR.

Main Methods:

  • A prospective, interventional study involving 1,757 patients with mild or no DR across four Thai centers.
  • Fundus photographs were analyzed by a deep learning model to predict progression risk.
  • Patients were scheduled for follow-up screenings based on the model's risk prioritization.

Main Results:

  • The deep learning model achieved 90.4% sensitivity in prioritizing patients who developed MOD+ DR within the first 50% of follow-up screens.
  • Model-proposed prioritization significantly outperformed random ordering (P < 0.001).
  • Excluding one site with implementation challenges, the model still showed high sensitivity (86.7%) compared to DR grade and HbA1c alone (73.3%).

Conclusions:

  • Deep learning models show potential for effective risk stratification in diabetic retinopathy (DR) screening.
  • Prioritization of follow-up visits for patients with mild/no DR is feasible using this model.
  • Further research is needed to evaluate the clinical management and outcomes impact of this technology.